Add HOL Guard to AI Agent Security

[kantorcodes]

Submission

• Resource: HOL Guard
• Canonical URL: https://hol.org/guard
• Suggested section: Open Source Security Tools > AI Agent Security
• Project launch date: 2026-03-28

MLSecOps relevance

HOL Guard is an open-source local-first runtime security layer for AI agents. It evaluates supported agent tool actions and local artifacts before trust or execution decisions, covering prompt injection, secret exposure, unsafe commands, package risks, and MCP threats. Practitioners can evaluate it from the public source, documented install flow, releases, support matrix, security policy, and local runtime behavior.

Field	Required information
Security use case	Runtime policy enforcement and pre-execution review for AI-agent actions and local agent artifacts
Protected component	AI agents, tool calls, MCP integrations, plugins, skills, packages, credentials, and local runtime state
Threat coverage	Prompt injection, secret exposure, unsafe commands, malicious or changed packages, MCP risks, and excessive or ambiguous tool actions
Evaluation	Public source and documentation; pipx install hol-guard; documented support matrix, approval flow, receipts, releases, and security policy
Maturity	Public repository since 2026-03-28; Apache-2.0 licensed; stable 2.x release channel with opt-in 3.x prereleases and active maintenance
Affiliation	I am affiliated with HOL / Hashgraph Online, which maintains HOL Guard

Technical review: Reviewed 2026-08-23. Evidence checked: https://github.com/hashgraph-online/hol-guard, https://github.com/hashgraph-online/hol-guard/blob/release/3.0/README.md, https://github.com/hashgraph-online/hol-guard/blob/main/LICENSE, https://github.com/hashgraph-online/hol-guard/releases, https://github.com/hashgraph-online/hol-guard/blob/release/3.0/docs/guard/harness-support.md, and https://github.com/hashgraph-online/hol-guard/blob/main/SECURITY.md.

Affiliation

• I have no material affiliation with this resource.
• I am affiliated with this resource.

If affiliated, describe the relationship: I am President of HOL and am materially affiliated with the organization that maintains HOL Guard.

Disclosure: I am affiliated with this project through HOL / Hashgraph Online.

Checklist

• I have read and followed the contribution guidelines.
• The resource addresses a concrete MLSecOps or AI-security problem.
• The resource is publicly usable or independently evaluable.
• The description is factual, neutral, and one sentence long.
• The canonical URL contains no referral or tracking parameters.
• This PR proposes one resource or one focused change.
• I have disclosed all relevant affiliations.

[kantorcodes]

Friendly bump for review when convenient. One-line addition under Open Source Security Tools > AI Agent Security with honest scope (local-first runtime control; scan ≠ safety guarantee). Disclosure: President of HOL / Hashgraph Online. Happy to reword.